Fireworks AI
Fast inference platform for OSS LLMs — custom Cuda kernels, speculative decoding, multi-LoRA serving. Targets latency-sensitive production use cases.
Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 20 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Fast OSS LLM inference cloud vendor fix
- Tier
- T1
- Section
- Inference platforms & gateways
- Latest release
- v1.2.30 (2026-10-21) — fireworks-ai registry fix
- License
- proprietary; Python SDK Apache-2.0 repo fix
- GitHub
- searched not found vendor fix
- Pricing
- Serverless pay-per-token; on-demand GPUs $8/hr (H100/H200), $13/hr (B200), $15/hr (B300); fine-tuning from $0.50 per 1M training tokens (LoRA SFT up to 16B) vendor fix
- Freshness
- 2026-10-27 fix
- Layer
- model-infra repo fix
- Licensing
- commercial repo fix
- SDK languages
- python, rest vendor fix
- Protocols
- mcp-client, openai-compatible vendor fix
- Compliance
- gdpr, hipaa, iso27001, iso27701, iso42001, soc2-type2 vendor fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
$52M Series B 2024-07 at $552M val (Sequoia led); ex-Meta PyTorch team.
Technical surface
- API surface
- OpenAI-compatible REST API, Python SDK (fireworks-ai)
- Backend storage
- not applicable — not a memory product
- Deployment
- searched not found
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Fireworks AI with…
Similar systems
Other inference platforms & gateways in the catalog, ranked by inbound references.
- LiteLLM T1
BerriAI's open-source LLM gateway — unified OpenAI-format API for 100+ providers; LiteLLM Proxy adds budgets, fallbacks, observability, rate-limiting.
- OpenRouter T1
Unified API + marketplace for 300+ models — pay-as-you-go credits, automatic fallback, model arena. Used as default LLM router by many JS/TS agents.
- Together AI T1
Cloud platform for OSS LLM inference and fine-tuning — serverless inference, dedicated endpoints, fine-tuning API, training cluster.
- vLLM T1
Open-source LLM inference engine with PagedAttention — high-throughput batching, paged KV-cache. UC Berkeley origin; de-facto OSS inference stack.
- Portkey AI T2
AI gateway + observability — load balancing across 200+ LLMs, retries, caching, eval, prompts. Open-source Gateway + commercial Portkey Cloud. Acquired by Palo Alto Networks (closed about 2026-06); now sold as Prisma AIRS AI Gateway (GA 2026-07-16).
- Baseten T1
Inference platform for ML models — Truss package format, Chains for multi-model workflows, autoscaling GPU/CPU serving. Targeted at production teams shipping LLM/diffusion endpoints.
Sources (19 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Fast OSS LLM inference cloud vendor
- What it does & what's distinct Fast inference platform for OSS LLMs — custom Cuda kernels, speculative decoding, multi-… vendor
- Claims / benefits $52M Series B 2024-07 at $552M val (Sequoia led); ex-Meta PyTorch team. vendor
- Created 2022 vendor
- Latest release v1.2.30 (2026-10-21) — fireworks-ai registry
- License proprietary; Python SDK Apache-2.0 repo
- Funding $77M total raised through Series B 2024-07 ($52M, Sequoia led; $552M valuation). vendor
- Customers / scale Cresta, Cursor, Liner, DoorDash, Quora; fast inference for OSS models + custom. vendor
- Pricing Serverless pay-per-token; on-demand GPUs $8/hr (H100/H200), $13/hr (B200), $15/hr (B300)… vendor
- HQ Redwood City, CA, USA. vendor
- Founders / pedigree Lin Qiao (CEO; ex-PyTorch lead at Meta), Dmytro Dzhulgakov; founded 2022. vendor
- API surface OpenAI-compatible REST API, Python SDK (fireworks-ai) vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup model-infra repo
- compliance-certifications gdpr,hipaa,iso27001,iso27701,iso42001,soc2-type2 vendor
- sdk-languages python,rest vendor
- protocol-support mcp-client,openai-compatible vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-27
- License first recorded as “proprietary; Python SDK Apache-2.0” source
- Latest release first recorded as “v1.2.30 (2026-10-21) — fireworks-ai” source
- Pricing first recorded as “Serverless pay-per-token; on-demand GPUs $8/hr (H100/H200), $13/hr (B200), $15/hr (B300); fine-tuning from $0.50 per 1M training tokens (LoRA SFT up to 16B)” source
Related systems
References (17)
- Bedrock AgentCore (AWS) integrates with — Fireworks AI docs integration: AWS AgentCore. (verified 2026-10-29)
- Claude Agent SDK integrates with — Fireworks AI docs integration: Claude Agent SDK (Nexus harness, preview). (verified 2026-10-29)
- Claude Code (Anthropic) integrates with — Fireworks AI docs integration: Claude Code (Nexus coding harness). (verified 2026-10-29)
- CrewAI integrates with — Fireworks AI docs integration: CrewAI. (verified 2026-10-29)
- Cursor (IDE) integrates with — Fireworks AI docs integration: Cursor IDE (Nexus harness, preview). (verified 2026-10-29)
- Helicone integrates with — Fireworks AI docs integration: Helicone (LLM Gateways). (verified 2026-10-29)
- LangChain (framework) integrates with — Fireworks AI docs integration: LangChain. (verified 2026-10-29)
- LiteLLM integrates with — Fireworks AI docs integration: LiteLLM (LLM Gateways; native fireworks_ai provider). (verified 2026-10-29)
- LlamaIndex (framework) integrates with — Fireworks AI docs integration: LlamaIndex. (verified 2026-10-29)
- MLflow integrates with — Fireworks AI docs integration: MLflow tracing (MLOps & Observability). (verified 2026-10-29)
- OpenAI Codex CLI integrates with — Fireworks AI docs integration: Codex (Nexus harness). (verified 2026-10-29)
- Opencode (SST) integrates with — Fireworks AI docs integration: OpenCode (Nexus harness). (verified 2026-10-29)
- OpenRouter integrates with — Fireworks AI docs integration: OpenRouter (upstream provider, LLM Gateways). (verified 2026-10-29)
- Portkey AI integrates with — Fireworks AI docs integration: Portkey (LLM Gateways). (verified 2026-10-29)
- Pydantic-AI integrates with — Fireworks AI docs integration: PydanticAI. (verified 2026-10-29)
- Strands Agents (AWS) integrates with — Fireworks AI docs integration: Strands Agents. (verified 2026-10-29)
- Weights & Biases integrates with — Fireworks AI docs integration: Weights & Biases (MLOps & Observability). (verified 2026-10-29)
Referenced by (24)
- agentgateway integrates with — agentgateway integrations docs have a Fireworks AI provider page. (verified 2026-10-29)
- Bifrost (Maxim AI) integrates with — Bifrost supported-providers docs have a provider page for Fireworks. (verified 2026-10-29)
- Braintrust integrates with — Braintrust docs have a Fireworks AI integration page. (verified 2026-10-29)
- Comet ML integrates with — Comet's Opik docs have a Fireworks AI integration page. (verified 2026-10-29)
- CrewAI integrates with — CrewAI LLM docs include a Fireworks AI provider configuration section. (verified 2026-10-29)
- Daytona integrates with — Daytona docs have a guide for running Fireworks AI with Daytona sandboxes. (verified 2026-10-29)
- Inspect AI integrates with — Inspect AI model-providers page documents a Fireworks AI provider. (verified 2026-10-29)
- LangChain (framework) integrates with — LangChain docs have a Fireworks integration provider page (Fast inference for open and proprietary language models). (verified 2026-10-29)
- Langfuse integrates with — Langfuse's integrations directory has a Fireworks AI integration page. (verified 2026-10-29)
- Letta / MemGPT integrates with — Letta models docs list Fireworks in the supported model provider table. (verified 2026-10-29)
- LiteLLM integrates with — LiteLLM docs have a Fireworks AI provider page. (verified 2026-10-29)
- LiveKit Agents integrates with — LiveKit Agents docs have a Fireworks AI model plugin page. (verified 2026-10-29)
- LlamaIndex (framework) integrates with — LlamaIndex has an official LLM integration package llama-index-llms-fireworks in its repo. (verified 2026-10-29)
- Milvus integrates with — Milvus's integrations overview lists a Milvus + Fireworks AI integration tutorial. (verified 2026-10-29)
- OpenRouter integrates with — OpenRouter lists Fireworks as an inference provider (providers API slug "fireworks"). (verified 2026-10-29)
- Phidata (now Agno) integrates with — Agno ships a fireworks model provider module (agno.models.fireworks). (verified 2026-10-29)
- Pipecat (Daily) integrates with — Pipecat docs have a Fireworks AI service page. (verified 2026-10-29)
- Portkey AI integrates with — Portkey docs have a Fireworks LLM provider integration page. (verified 2026-10-29)
- Pydantic-AI integrates with — Pydantic AI "Other compatible APIs" docs have a Fireworks AI section. (verified 2026-10-29)
- Strands Agents (AWS) integrates with — Strands Agents docs have a community Fireworks AI model provider integration page. (verified 2026-10-29)
- Supabase Vector integrates with — Supabase's AI & Vectors docs have a Fireworks AI integration page. (verified 2026-10-29)
- Temporal integrates with — Temporal integrations catalog lists Fireworks AI model-provider integration. (verified 2026-10-29)
- TrueFoundry AI Gateway integrates with — TrueFoundry AI Gateway ecosystem lists a Fireworks integration page. (verified 2026-10-29)
- Vercel AI SDK integrates with — AI SDK docs have a Fireworks official AI SDK provider page. (verified 2026-10-29)